pith. sign in

arxiv: 2006.07886 · v3 · pith:FI45EZ2Knew · submitted 2020-06-14 · 💻 cs.LG · stat.ML

On Disentangled Representations Learned From Correlated Data

classification 💻 cs.LG stat.ML
keywords datadisentanglementapproachescorrelatedcorrelationsindependentlatentlearned
0
0 comments X
read the original abstract

The focus of disentanglement approaches has been on identifying independent factors of variation in data. However, the causal variables underlying real-world observations are often not statistically independent. In this work, we bridge the gap to real-world scenarios by analyzing the behavior of the most prominent disentanglement approaches on correlated data in a large-scale empirical study (including 4260 models). We show and quantify that systematically induced correlations in the dataset are being learned and reflected in the latent representations, which has implications for downstream applications of disentanglement such as fairness. We also demonstrate how to resolve these latent correlations, either using weak supervision during training or by post-hoc correcting a pre-trained model with a small number of labels.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations

    cs.LG 2026-05 unverdicted novelty 7.0

    CAML meta-learns a progressively refined inductive bias from active-learning queries to improve robustness to spurious correlations, reporting accuracy gains on minority groups across several benchmarks.

  2. Deep Attention Reweighting: Post-Hoc Attention-Based Feature Aggregation in CNNs for Disentangling Core and Spurious Features under Spurious Correlations

    cs.CV 2026-05 unverdicted novelty 5.0

    DAR replaces GAP with an attention-based aggregation module retrained jointly with the classifier head to disentangle core from spurious features and outperforms DFR on multiple datasets.